Plachtaa / VITS-fast-fine-tuning

This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion
Apache License 2.0
4.69k stars 705 forks source link

將英文文本給 cmd_inference.py 執行無法生成wav音檔, 但將文本中的空格去除後才有辦法生成音檔 #462

Closed AshenJie6 closed 11 months ago

AshenJie6 commented 11 months ago

如題, 將英文文本(e.g. Hello! How can I assist you today?)給 cmd_inference.py 去執行, 沒辦法生成wav檔. 但將文檔中的空格去除調後(e.g. Hello!HowcanIassistyoutoday?)才有辦法生成音檔, 但這樣的方式會讓生成的音檔亂念一通. 請問這個問題該如何解決呢?

附上我消除空格的方式: os.system('python cmd_inference.py -m G_latest.pth -c finetune_speaker.json -l English -s Adam50 -t ' + reply.replace(' ', '') + ' > /dev/null 2>&1')

AshenJie6 commented 11 months ago

問題已解決